Training in progress, step 9980, checkpoint

last-checkpoint/optimizer.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6cdb2a5a901c63b779f1866ebf5cde2e6a49a922c05207376e7847a8df285914
+oid sha256:c7790db1cbcec3751495fdd44579dedc5ab72558fd38144d6ff0afd0bec6da03
 size 1657

last-checkpoint/rng_state.pth

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:36579bea99df82fd100f51f078b75ec7090161b4f6090440eb87c9a54ca32412
+oid sha256:5186a963c4bbb62c9b5731d6c65fa0aadbeff1c2051f9ef31571be06d9388864
 size 14709

last-checkpoint/scheduler.pt

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:26906f9180f00219fff96ef9a710000390990b70abeaa78af7e691112ec5c682
+oid sha256:ea4d37eccc5be27331c5c923a231c3d00483b5e7cd0ef06b413ba155456540dd
 size 1465

last-checkpoint/trainer_state.json

@@ -2,9 +2,9 @@
   "best_global_step": null,
   "best_metric": null,
   "best_model_checkpoint": null,
-  "epoch": 76.6923076923077,
+  "epoch": 76.76923076923077,
   "eval_steps": 500,
-  "global_step": 9970,
+  "global_step": 9980,
   "is_hyper_param_search": false,
   "is_local_process_zero": true,
   "is_world_process_zero": true,
@@ -17954,6 +17954,24 @@
       "mean_token_accuracy": 0.6652602583169938,
       "num_tokens": 36360871.0,
       "step": 9970
+    },
+    {
+      "epoch": 76.73076923076923,
+      "grad_norm": 0.0,
+      "learning_rate": 1.3e-07,
+      "loss": 1.7443,
+      "mean_token_accuracy": 0.6487196087837219,
+      "num_tokens": 36379371.0,
+      "step": 9975
+    },
+    {
+      "epoch": 76.76923076923077,
+      "grad_norm": 0.0,
+      "learning_rate": 1.05e-07,
+      "loss": 1.737,
+      "mean_token_accuracy": 0.6534163296222687,
+      "num_tokens": 36398038.0,
+      "step": 9980
     }
   ],
   "logging_steps": 5,
@@ -17973,7 +17991,7 @@
       "attributes": {}
     }
   },
-  "total_flos": 1.8439063535429222e+18,
+  "total_flos": 1.8457508908847923e+18,
   "train_batch_size": 4,
   "trial_name": null,
   "trial_params": null